Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and closed-corpus scope are partly covered. The description adds genuinely new behavior: it clarifies the corpus is 'published' guides only and specifies the return shape ('matching articles with summaries and links to full Markdown'), which matters given there is no output schema. It omits result ordering/relevance behavior and limits, but the core behavioral picture is conveyed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and resource, then the topic taxonomy, then the explicit use case. The topic list is long but earns its space by signalling index coverage, which an agent cannot get from the schema. Slightly dense, but no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter read-only search with no output schema, the definition covers what the tool searches, what it returns (articles plus summaries and Markdown links), and the intended question types. Missing pieces are minor: no guidance on refining a zero-result query or on how results are ranked.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — query (with concrete example keywords), limit (1-10, default 5) and language (en/es/pl/any enum) are all documented in the schema itself. The description does not add syntax, matching behavior, or ranking semantics beyond what the schema states, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource ('Search Bramvia's published guides') and enumerates topical coverage (Business Central, ERP migrations, AI in ERP, SII/Verifactu/DeCA/KSeF localization, tariffs/landed cost). This is far more than a restatement of the name. It stops short of 5 because it never distinguishes itself from topically overlapping siblings such as get_bramvia_article (article retrieval) or check_compliance_deadlines (computed deadlines vs. guide text).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one positive usage cue: 'Use this for factual questions about Business Central, ERP migration cost and method, or compliance deadlines.' However, 'compliance deadlines' is exactly what check_compliance_deadlines and check_deca_obligation appear to do, and the description never says when to prefer the searchable guides over those deterministic tools, nor any when-not-to-use condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.